© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 465
    Prev
    Next
    INDEX
    Explanations

    precedes descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite

    small sizes or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ড্রিম
    0.51
     ሞ
    0.48
    uire
    0.46
    ontiti
    0.46
    이트
    0.45
     архі
    0.45
    니다
    0.43
     자연
    0.43
    nimi
    0.43
     ідэ
    0.42
    POSITIVE LOGITS
    concatenate
    0.44
    涉及
    0.43
    〆
    0.42
    集中
    0.42
    角落
    0.42
     Bryn
    0.41
     einzel
    0.41
     küçük
    0.40
     yanı
    0.40
    个
    0.40
    Activations Density 0.000%

    No Known Activations